Files
ModelHub XC dd6a4f7f8c 初始化项目,由ModelHub XC社区提供模型
Model: jdineen/olmo3-7b-pilot5-dpo-instrumental
Source: Original Platform
2026-05-25 05:03:18 +08:00

62 lines
1.4 KiB
JSON

{
"architectures": [
"Olmo3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0,
"eos_token_id": 100257,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"layer_types": [
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention"
],
"max_position_embeddings": 8192,
"model_type": "olmo3",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pad_token_id": 100277,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 500000,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.55.4",
"use_cache": false,
"vocab_size": 100278
}